Nabla Transcription API

Medical-grade speech-to-text endpoints.

OpenAPI Specification

nabla-transcription-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: Nabla Core Authentication Transcription API
  description: 'Nabla provides ambient AI for clinicians. The Core API supports

    transcription (synchronous, asynchronous, and WebSocket) of medical

    encounters. The Server API issues OAuth 2.0 access tokens via JWT

    client credentials, and the User API exchanges per-user JWT tokens

    so that client applications can call the Core API on behalf of a

    Copilot user.

    '
  version: '1.0'
servers:
- url: https://api.nabla.com
  description: Nabla production API
security:
- bearerAuth: []
tags:
- name: Transcription
  description: Medical-grade speech-to-text endpoints.
paths:
  /server/transcribe:
    post:
      tags:
      - Transcription
      summary: Transcribe a short audio file (synchronous)
      description: 'Synchronous transcription of recorded audio up to 10 minutes in

        length. Returns the transcript inline.

        '
      operationId: serverTranscribe
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - audio
              properties:
                audio:
                  type: string
                  format: binary
                language:
                  type: string
      responses:
        '200':
          description: Transcript payload.
          content:
            application/json:
              schema:
                type: object
  /server/transcribe-async:
    post:
      tags:
      - Transcription
      summary: Submit an audio file for asynchronous transcription
      description: 'Submit recorded audio (up to 60 minutes) for asynchronous

        transcription. Results are delivered via callback or polled by

        identifier.

        '
      operationId: serverTranscribeAsync
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - audio
              properties:
                audio:
                  type: string
                  format: binary
                callback_url:
                  type: string
                  format: uri
                language:
                  type: string
      responses:
        '202':
          description: Transcription job accepted.
          content:
            application/json:
              schema:
                type: object
                properties:
                  job_id:
                    type: string
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: OAuth 2.0 access token (Server API) or JWT access token (User API).